Use this skill after a plan has been approved and development is about to start. Breaks down the implementation into independent work streams that can be executed by subagents in parallel. Each subagent has access to all available skills. Trigger when transitioning from planning to implementation, especially for multi-file or multi-component work.
Use this skill when writing or reviewing code to ensure changes are minimal, clear, and spec-aligned. Catches scope creep in code, removes unnecessary additions, and enforces repo standards. Trigger during code review or before committing changes.
Use this skill after design decisions or major code changes to update documentation. Creates per-directory CLAUDE.md files and maintains top-level CLAUDE.md and ARCHITECTURE.md. Trigger after completing features, refactoring, or architectural changes.
Use this skill when installing libraries, choosing dependencies, or integrating with external APIs and frameworks. Activates research mode to find the latest maintained libraries, discover deprecations, and gather current best practices. Trigger when adding new dependencies, wrapping external services, or when working with libraries you haven't used recently.
Use this skill after every code change to run linting and type checking. Ensures code passes all lint checks, types are correct and consistent, and typing patterns match repo conventions. Trigger after writing or modifying code.
Use this skill when defining requirements, scoping features, or clarifying what to build and why. Activates a product manager mindset focused on business alignment, scope control, and clarity. Trigger when starting a new feature, refining requirements, or when scope seems to be expanding.
Use this skill when creating a new Python project or setting up tooling for an existing one. Runs pyscaffold, configures pre-commit with comprehensive hooks, and sets up CLAUDE.md for documentation. Trigger when starting new projects or adding standard tooling.
Use this skill when the user wants you to reason through a problem with extra rigor and self-criticism. Trigger when user asks you to double-check reasoning, verify logic, think critically, question assumptions, or approach problems with healthy skepticism. Also use when solving complex problems where errors would be costly.